EP3925845A1 - Verfahren zur vorhersage der aktion eines anderen fahrzeugs und vorrichtung zur vorhersage der aktion eines anderen fahrzeugs - Google Patents
Verfahren zur vorhersage der aktion eines anderen fahrzeugs und vorrichtung zur vorhersage der aktion eines anderen fahrzeugs Download PDFInfo
- Publication number
- EP3925845A1 EP3925845A1 EP19914188.8A EP19914188A EP3925845A1 EP 3925845 A1 EP3925845 A1 EP 3925845A1 EP 19914188 A EP19914188 A EP 19914188A EP 3925845 A1 EP3925845 A1 EP 3925845A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- vehicle
- lane
- lane change
- probability
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000033001 locomotion Effects 0.000 claims abstract description 172
- 238000012937 correction Methods 0.000 claims description 121
- 230000001133 acceleration Effects 0.000 claims description 30
- 230000001965 increasing effect Effects 0.000 claims description 16
- 230000006399 behavior Effects 0.000 description 25
- 230000006870 function Effects 0.000 description 13
- 230000015654 memory Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 230000010365 information processing Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0022—Gains, weighting coefficients or weighting functions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
- B60W2050/0052—Filtering, filters
- B60W2050/0054—Cut-off filters, retarders, delaying means, dead zones, threshold values or cut-off frequency
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4042—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4044—Direction of movement, e.g. backwards
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4045—Intention, e.g. lane change or imminent movement
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data
Definitions
- the present invention relates to a motion prediction method of other vehicle and a motion prediction apparatus of other vehicle.
- Patent Literature 1 Since some time ago, an apparatus has been known that predicts an interruption by a second vehicle, which is running in an adjacent lane adjacent to an own driving lane in which an own vehicle is running, into the own driving lane and controls a vehicle speed of the own vehicle (refer to Patent Literature 1).
- the apparatus disclosed in the Patent Literature 1 computes an angle formed by a moving vector of the second vehicle with respect to a directional vector of a white line painted on a road surface and, if the angle exceeds a predetermined threshold angle, determines an interruption by the second vehicle into the own driving lane.
- Patent Literature 1 Japanese Unexamined Patent Application Publication No. 2001-199260
- the width of a lane in which the own vehicle drives is not constant and differs road by road and the above-mentioned Patent Literature 1 does not put this into consideration. If the lane width differs, a vehicle behavior of the second vehicle will differ when a vehicle conducts a course change, to cause a possibility of causing an erroneous determination or a determination delay.
- the present invention has been made in consideration of the above-mentioned problems and an object thereof is to provide a motion prediction method of other vehicle and an apparatus for motion prediction of other vehicle for suppressing an erroneous motion prediction of other vehicle or a prediction delay.
- a first aspect of the present invention is a motion prediction method of other vehicle that computes, based on a behavior of a second vehicle running in an adjacent lane, a lane change probability indicating a probability of the second vehicle conducting a lane change in front of an own vehicle from the adjacent lane into an own lane in which the own vehicle is running and, with use of the lane change probability and a threshold value, predicts the lane change to be conducted by the second vehicle.
- the motion prediction method of other vehicle obtains information indicating a lane width of the adjacent lane, corrects, according to the lane width of the adjacent lane, at least one of the lane change probability and threshold value, and by comparing the after-correction lane change probability with the before-correction threshold value, or by comparing the before-correction lane change probability with the after-correction threshold value, or by comparing the after-correction lane change probability with the after-correction threshold value, determines whether or not the second vehicle conducts the lane change.
- a second aspect of the present invention is a motion prediction method of other vehicle that computes, based on a behavior of a second vehicle running in an adjacent lane, a lane change probability indicating a probability of the second vehicle conducting a lane change in front of an own vehicle from the adjacent lane into an own lane in which the own vehicle is running and, with use of the lane change probability and a threshold value, predicts the lane change to be conducted by the second vehicle.
- the motion prediction method of other vehicle obtains information indicating a position of the second vehicle, corrects, according to the position of the second vehicle, at least one of the lane change probability and threshold value, and by comparing the after-correction lane change probability with the before-correction threshold value, or by comparing the before-correction lane change probability with the after-correction threshold value, or by comparing the after-correction lane change probability with the after-correction threshold value, determines whether or not the second vehicle conducts the lane change.
- the first aspect and second aspect of the present invention it is possible to suppress erroneously predicting a movement of the second vehicle or delaying a prediction.
- FIG. 4A illustrates, on a one-way road formed of two lanes (G1, G2), a driving scene in which an own vehicle 11 is running in the left lane (own lane) G1 and a second vehicle 12 is running in the right lane (adjacent lane) G2 that is a lane adjacent to the own lane.
- the second vehicle 12 is running in diagonal front of the own vehicle 11.
- Fig. 4B differs from Fig. 4A in that Fig.
- FIG. 4B is a one-way road formed of two lanes (G1, G2) whose width of a lane (hereunder called the "lane width") is wider than that of the two lanes (G1, G2) of Fig. 4A .
- the other parts of the driving scene of Fig. 4B are the same as those of the driving scene of Fig. 4A .
- the second vehicle 12 may be running by any one of automated driving and manual driving.
- the "automated driving” is a driving mode that a predetermined vehicle drive control device actively conducts a part or the whole of recognition, decision, and operation related to vehicle driving.
- the “manual driving” is a driving mode that a driver, i.e., an occupant (human) of the second vehicle 12 conducts the vehicle driving.
- the first embodiment computes a lane change probability according to a behavior of the second vehicle 12 and, with use of the lane change probability and a threshold value, predicts a lane change to be conducted by the second vehicle 12. In other words, with use of the lane change probability and threshold value, a determination is made whether or not the second vehicle 12 conducts a lane change.
- the "lane change probability” indicates a probability that the second vehicle 12 may conduct a lane change in front of the own vehicle 12 from the adjacent lane G2 to the own lane G1.
- the "lane change” is an example of movements of the second vehicle 12.
- the attitude (including a running direction, an axle direction, and a yaw angle), moving direction, moving distance (proximity quantity) in a vehicle width direction, and driving path of the second vehicle 12 change depending on the lane width (32a, 32b) of the adjacent lane G2.
- the first embodiment obtains information indicating the lane width (32a, 32b) of the adjacent lane G2 and, according to the lane width (32a, 32b), corrects at least one of the lane change probability and threshold value. Thereafter, the first embodiment compares the after-correction lane change probability with the before-correction threshold value, or compares the before-correction lane change probability with the after-correction threshold value, or compares the after-correction lane change probability with the after-correction threshold value, and thereby predicts a lane change to be conducted by the second vehicle 12.
- Taking the lane width (32a, 32b) of the adjacent lane G2 into consideration in predicting a lane change makes it possible to suppress an erroneous lane change prediction or a prediction delay.
- Which of the lane change probability and threshold value is corrected can be chosen by a user (for example, the driver of the own vehicle 11).
- driving scenes such as those illustrated in Figs. 4A and 4B are examples of driving scenes in which the motion prediction method of other vehicle and the motion prediction apparatus of other vehicle according to the first embodiment effectively function and are not intended to limit scopes to which the motion prediction method of other vehicle and the motion prediction apparatus of other vehicle according to the first embodiment are applicable.
- the motion prediction apparatus of other vehicle has a control unit.
- the control unit predicts that, based on a behavior of the second vehicle 12 running in the adjacent lane G2, the second vehicle 12 may conduct a lane change in front of the own vehicle 11 from the adjacent lane G2 to the own lane G1.
- the control unit has an object detect part 102, an own vehicle position estimate part 101, a lane structure obtain part 104, and a microcomputer.
- the object detect part 102 is mounted on the own vehicle 11 and includes a plurality of different kinds of object detect sensors such as a laser radar, a millimeter-wave radar, a camera, a LiDAR (Light Detection and Ranging), and the like to detect objects around the own vehicle 11.
- the object detect part 102 uses the plurality of object detect sensors and detects objects around the own vehicle 11.
- the object detect part 102 detects the second vehicle 12 such as a two-wheel vehicle, a light vehicle such as a bicycle, a moving object such as a pedestrian, and a motionless object such as a parked vehicle.
- the second vehicle 12 is a lane change determination object and whose behavior corresponds to a "state quantity" used to compute a lane change probability.
- the object detect part 102 consolidates a plurality of detection results obtained from the plurality of object detect sensors and outputs one detection result for each object. More precisely, from behaviors of an object obtained from the respective object detect sensors, it computes, taking the error characteristics and the like of the respective object detect sensors into consideration, a most reasonable and least erroneous behavior of the object. In more detail, it uses a known sensor fusion technique to generally evaluate the detection results obtained from the plural kinds of sensors and obtains a more correct detection result.
- the object detect part 102 tracks the detected object. More precisely, from the consolidated detection result and from behaviors of the object outputted at different times, verifies (corresponds) the sameness of the object between the different times, and based on the correspondence, predicts a behavior of the object. By the way, the behaviors of the object outputted at different times are stored in a memory in the microcomputer and are used for a movement prediction of the second vehicle 12 to be explained later.
- the object detect part 102 outputs, as a detection result, a behavior of a two-dimensional object with, for example, a top view of the own vehicle 11 seen from the air above.
- the behavior of the second vehicle 12 is expressed with any one of or a combination of two or more of the position including an absolute position and a relative position, attitude, moving direction, speed, acceleration, and drive path of the second vehicle 12.
- the drive path of the second vehicle 12 indicates a time series of positions of the second vehicle 12.
- the behavior of the second vehicle 12 includes a profile of positions of the second vehicle 12 at different times and a profile of speeds of the second vehicle at the respective positions.
- the behavior of the second vehicle 12 can be expressed with one or a combination of two or more of an angle formed by the attitude or moving direction of the second vehicle 12 with respect to a lane direction of the adjacent lane (right lane G2) or of the own lane (left lane G1), a lane width directional position of the second vehicle 12 in the adjacent lane, a speed of the second vehicle 12, an acceleration of the second vehicle 12, and a deceleration of the second vehicle 12.
- the own vehicle position estimate part 101 has a position detect sensor such as a receiver to receive a GPS (Global Positioning System) signal, to measure the position (absolute position) and attitude (absolute attitude) of the own vehicle 11 on terrestrial coordinates. Further, the own vehicle position estimate part 101 has a computation processing circuit to carry out odometry and dead reckoning. More precisely, the own vehicle position estimate part 101 employs a wheel velocity sensor for detecting the wheel velocity of each wheel of the own vehicle 11, a steering angle sensor for detecting the steering angle of a steering wheel, and computation processing circuits, to measure the relative position, relative attitude, and speed of the own vehicle 11 with respect to a predetermined reference point.
- a position detect sensor such as a receiver to receive a GPS (Global Positioning System) signal
- GPS Global Positioning System
- attitude absolute attitude
- the own vehicle position estimate part 101 has a computation processing circuit to carry out odometry and dead reckoning. More precisely, the own vehicle position estimate part 101 employs a wheel velocity sensor for detecting the wheel velocity
- the own vehicle position estimate part 101 is able to detect, from the information indicating the position and attitude of the own vehicle 11, the position and attitude of the own vehicle 11 on a map.
- the map is provided by map data stored in advance in a map database 111.
- the lane structure obtain part 104 obtains information indicating the structure of a road including the left lane G1 and right lane G2 and the structure of each lane (G1, G2) forming the road.
- the motion prediction apparatus of other vehicle may have the map database 111.
- Map data stored in the map database 111 contains data indicating the structure of the road including the own lane G1 and right lane G2 and the structure of each lane forming the road.
- the lane structure obtain part 104 accesses the map database 111 and is able to obtain the information (map data) indicating the road structure and lane structure.
- the lane structure obtain part 104 may obtain not only the map data but also information (traffic rules information) indicating traffic rules related to roads around the own vehicle 11.
- the map database 111 stores traffic rules information linked to road structures and lane structures.
- the information indicating a lane structure obtained by the lane structure obtain part 104 contains information indicating the lane width of each lane (G1, G2).
- the map database 111 may store information indicating the lane width of each lane (G1, G2).
- the information obtained by the lane structure obtain part 104 is temporarily stored in the memory of the microcomputer to be explained later.
- the map database 111 may be installed in the own vehicle 11 or may not be installed therein. If not installed, the lane structure obtain part 104 may obtain the map data and traffic rules information from the outside of the vehicle, for example, from Intelligent Transport System (ITS) or Universal Traffic Management System (UTMS) through vehicle-to-vehicle and vehicle-to-road communications or mobile telecommunications such as 3G and LTE.
- ITS Intelligent Transport System
- UTMS Universal Traffic Management System
- the lane structure obtain part 104 may employ the camera of the object detect part 102 to obtain an image around the own vehicle 11 and recognize, from the image, road-painted lane markings and road signs indicating road traffic regulations and instructions.
- the lane structure obtain part 104 is able to obtain, from the recognized lane markings, a road structure, a lane structure, and traffic rules information.
- the lane markings painted on a road include a lane boundary line 31 to separate the adjacent lane (right lane G2) from the own lane (left lane G1), a lane marking 35 (including a road outside line) to separate the left lane G1 from a road shoulder or roadside strip adjacent to the left lane G1, and a lane marking 36 (including a road outside line) to separate the right lane G2 from a road shoulder or roadside strip adjacent to the right lane G2.
- the lane structure obtain part 104 may obtain, from the lane boundary line 31 and lane marking 35, information indicating a lane width of the left lane G1 and obtain, from the lane boundary line 31 and lane marking 36, information indicating a lane width of the right lane G2.
- the microcomputer determines, according to the detected result from the object detect part 102, the estimated result from the own vehicle position estimate part 101, and the obtained information from the lane structure obtain part 104, whether or not the second vehicle 12 conducts a lane change.
- the microcomputer is a general microcomputer having a CPU (Central Processing Unit), memories such as RAMs and ROMs, and an input/output part.
- the microcomputer is installed with a computer program (a program of motion prediction of other vehicle) to make it function as a part of the motion prediction apparatus of other vehicle.
- the microcomputer functions as a plurality of information processing circuits (103, 105, 108) of the motion prediction apparatus of other vehicle.
- the plurality of information processing circuits (103, 105, 108) of the motion prediction apparatus of other vehicle are realized by software.
- the plurality of information processing circuits (103, 105, 108) may be formed from discrete hardware. Further, the information processing circuits (103, 105, 108) may be realized by electronic control units (ECUs) that are also used for other controlling purposes of the own vehicle 11. According to the embodiment, as an example, the microcomputer also realizes information processing circuits (109, 110) to execute automated driving of the own vehicle 11 according to a motion prediction of other vehicle result.
- ECUs electronice control units
- the microcomputer has, as the plurality of information processing circuits (103, 105, 108 to 110), a movement option generate part 103, a probability compute part 105, a movement prediction determine part 108, an own vehicle path generate part 109, and a vehicle control part 110.
- the movement option generate part 103 predicts, according to the road structure and lane structure, movement options to be achieved in the near future by the second vehicle 12.
- the movement options predicted by the movement option generate part 103 include a lane change.
- the movement option generate part 103 predicts, according to the road structure and the structure of the lane (adjacent lane G2) to which the second vehicle 12 belongs, a movement intention how the second vehicle 12 runs next and computes a base path of the second vehicle according to the movement intention.
- the "movement option” is a higher concept including the movement intention and base path.
- the "base path" indicates not only a positional profile of the second vehicle at different times but also a speed profile of the second vehicle 12 at respective positions.
- the movement option generate part 103 predicts, as illustrated in Fig. 4A , a movement intention that the second vehicle 12 continues to run in the adjacent lane (right lane G2) and computes a base path running along the shape of the right lane G2. Further, the movement option generate part 103 predicts a movement intention that the second vehicle 12 conducts a lane change in front of the own vehicle 11 from the adjacent lane (right lane G2) to the own lane (left lane G1). Then, the movement option generate part 103 computes, according to the structure of the right lane G2 and the structure of the left lane G1, a base path along which the second vehicle conducts the lane change in front of the own vehicle 11 from the right lane G2 to the left lane G1.
- the "lane change” includes, as illustrated in Fig. 4A , a lane change to be conducted in a driving scene in which no train of vehicles is formed in the left lane G1 in front of the own vehicle 11, i.e., a so-called "normal lane change”.
- the "lane change” also includes a so-called “interruption” that is made into a train of vehicles formed in front of the own vehicle 11 in the own lane G1.
- the "interruption” is synonymous with a "cut in”.
- the probability compute part 105 computes a lane change probability according to a state quantity related to a lane change of the second vehicle 12 (hereunder simply the state quantity).
- the "lane change probability” indicates a probability of the second vehicle 12 conducting a lane change in front of the own vehicle 11 from the adjacent lane (right lane G2) to the own lane (left lane G1).
- the probability compute part 105 computes the lane change probability according to an angle ⁇ (an example of behaviors) formed by a moving direction of the second vehicle 12 and a lane direction of the right lane G2.
- the probability compute part 105 refers to a table illustrated in Fig.
- the lane direction of the right lane G2 corresponds to the running direction of a vehicle running along the right lane G2. Instead of the lane direction, it is possible to use a direction of the lane boundary line 31 separating the left lane G1 from the right lane G2.
- the probability compute part 105 may compute a lane change probability with use of, as a state quantity of the second vehicle 12, not only the angle ⁇ but also an attitude (a yaw angle with respect to the right lane G2) of the second vehicle 12 or a behavior of the second vehicle 12 such as a moving direction of the second vehicle 12 based on, for example, the own vehicle instead of the right lane G2.
- the state quantity may be a quantity expressing a proximity degree of the second vehicle 12 to the own vehicle 11 (hereunder simply the proximity quantity), i.e., a first proximity quantity or second proximity quantity to be explained later.
- the "first proximity quantity” indicates a vehicle width directional distance (33a, 33b) from a center of the own vehicle 11 to a center of the second vehicle 12.
- the “first proximity quantity” may be a vehicle width directional distance from a right side face of the own vehicle 11 to a left side face of the second vehicle 12.
- the “second proximity quantity” indicates a vehicle width directional distance (34a, 34b) from the lane boundary line 31 to the center of the second vehicle 12.
- the “second proximity quantity” may be a vehicle width directional distance from the lane boundary line 31 to the left side face of the second vehicle 12.
- the probability compute part 105 may refer to the table of Fig. 8 . If the second proximity quantity is 2.0 [m], the lane change probability is zero. If the second proximity quantity is 1.0 [m] or zero [m], the lane change probability is 0.5 or 1.0. Namely, the probability compute part 105 computes a higher lane change probability as the second proximity quantity becomes smaller. For example, it is possible to beforehand prepare, also for the first proximity quantity, a table similar to that of Fig. 8 and beforehand store it in the memory of the microcomputer.
- the data illustrated in the table of Fig. 8 is stored in the memory of the microcomputer in advance.
- the probability compute part 105 corrects the lane change probability according to the lane width (32a, 32b) of the adjacent lane (right lane G2). More precisely, the probability compute part 105 changes, based on the lane width (32a, 32b), a weight applied to a lane change probability computed according to a state quantity (including the above-mentioned "behavior” and "proximity quantity") used to compute the lane change probability. For example, an angle ⁇ in the case of the narrow lane width (32a) illustrated in Fig. 4A is compared with an angle ⁇ in the case of the wide lane width (32b) illustrated in Fig. 4B .
- the probability compute part 105 increases, as the lane width becomes smaller, the weight applied to the lane change probability computed according to the angle ⁇ . Multiplying the lane change probability computed with use of the angle ⁇ by the increased weight results in enhancing the angle ⁇ on the computation of the lane change probability (increases an influence of the angle ⁇ on the lane change probability).
- the probability compute part 105 changes, according to the lane width (32a, 32b), the weight applied to the lane change probability computed according to the angle ⁇ that is an example of state quantities, thereby correcting the lane change probability computed with use of the angle ⁇ .
- the probability compute part 105 is able to correct such that, with respect to the same angle ⁇ , the lane change probability increases as the lane width (32b) becomes narrower.
- the probability compute part 105 changes, according to the lane width (32a, 32b) similar to the case of the angle ⁇ , the weight applied to the lane change probability computed according to the attitude of the second vehicle 12 or the moving direction of the second vehicle 12.
- the probability compute part 105 changes, according to the lane width (32a, 32b), a weight applied to a lane change probability computed according to a proximity quantity (first proximity quantity, second proximity quantity) used to compute the lane change probability.
- a proximity quantity first proximity quantity, second proximity quantity
- the second vehicle 12 is able to determine a lane change at a proximity quantity smaller than that of the wide lane width (32b).
- the lane width (32a, 32b) becomes narrower, a vehicle width directional distance for which the second vehicle 12 moves to conduct a lane change becomes shorter so that the lane change becomes easier to conduct.
- the probability compute part 105 increases, as the lane width becomes narrower, the weight applied to the lane change probability computed according to the proximity quantity (first proximity quantity, second proximity quantity). Due to the weight increase, multiplying the lane change probability computed with use of the state quantity (first proximity quantity, second proximity quantity) by the weight results in enhancing the first proximity quantity and second proximity quantity when computing the lane change probability (increasing an influence of the first proximity quantity and second proximity quantity on the lane change probability). In this way, changing the weight applied to the lane change probability computed according to the first proximity quantity or second proximity quantity realizes the correction of a lane change probability computed with use of the first proximity quantity or second proximity quantity.
- the state quantity may be an acceleration of the second vehicle 12 or a proximity degree of the second vehicle 12 with respect to a first preceding vehicle 13a running in front of the second vehicle 12 in the adjacent lane (right lane G2).
- the "proximity degree” indicates, as illustrated in Figs. 5A and 5B , a distance 37 from a front end of the second vehicle 12 to a rear end of the first preceding vehicle 13a in a running direction (direction along the lane) or an acceleration in an approaching direction to the first preceding vehicle 13a.
- the probability computer part 105 computes a higher lane change probability as the acceleration or proximity degree of the second vehicle 12 becomes higher.
- a table similar to that of Fig. 8 may be prepared in advance for the acceleration or proximity degree of the second vehicle 12 and stored in advance in the memory of the microcomputer.
- the probability compute part 105 is able to make a correction, for the same acceleration or proximity degree, to increase the lane change probability as the lane width (32a, 32b) becomes narrower.
- the case of the narrower lane width ( Fig. 5A ) provides a higher lane change provability than the case of the wide lane width ( Fig. 5B ).
- the state quantity may be, as illustrated in Figs. 6A and 6B , an inter-vehicle distance between the second vehicle 12 and the own vehicle 11 (hereunder called the "first inter-vehicle distance (38a, 38b)").
- the first inter-vehicle distance (38a, 38b) is a running directional distance from a front end of the own vehicle 11 to a rear end of the second vehicle 12.
- the first inter-vehicle distance (38a, 38b) may be a distance from a gravity center position 11g of the own vehicle 11 to a gravity center position 12g of the second vehicle 12. Contrary to the second proximity quantity in the table of Fig.
- the probability compute part 105 computes a lower lane change probability as the first inter-vehicle distance (38a, 38b) becomes shorter.
- a table similar to that of Fig. 8 may be prepared in advance for the first inter-vehicle distance (38a, 38b) and stored in advance in the memory of the microcomputer.
- the probability compute part 105 is able to correct such that, with respect to the same first inter-vehicle distance, the lane change probability increases as the lane width (32a, 32b) becomes narrower.
- the state quantity may be, as illustrated in Figs. 7A to 7C , a distance between the own vehicle 11 and a second preceding vehicle 14 running in front of the own vehicle 11 in the own lane (left lane G1) (hereunder called the "second inter-vehicle distance (39a, 39b)").
- the second inter-vehicle distance (39a, 39b) is a running directional distance from a front end of the own vehicle 11 to a rear end of the second preceding vehicle 14. The longer the second inter-vehicle distance (39a, 39b), the wider the space for allowing the second vehicle 12 to cut into between the own vehicle 11 and the second preceding vehicle 14, to make the second vehicle 12 conduct a lane change easier.
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes narrower, a weight applied to a lane change probability computed according to the second inter-vehicle distance (39a, 39b).
- the second inter-vehicle distance (39a, 39b) is enhanced as the lane width becomes narrower.
- the probability compute part 105 is able to correct such that, with respect to the same second inter-vehicle distance, the lane change probability increases as the lane width (32a, 32b) becomes narrower.
- the state quantity may be, as illustrated in Figs. 5A and 5C , a difference between the size of the second vehicle 12 and the size of the first preceding vehicle (13a, 13b) running in front of the second vehicle 12 in the adjacent lane (right lane G2).
- the "size" of a vehicle is a concept including the height and width of the vehicle. For example, as illustrated in Fig. 5C , when the first preceding vehicle 13b is larger than the second vehicle 12, a front dead angle in the running direction of the second vehicle 12 formed by the first preceding vehicle 13b is wider compared with that of Fig. 5A . This makes it difficult for the second vehicle 12 to grasp a front situation in the running direction, thereby leading to a lower lane change probability.
- the probability compute part 105 computes a lower lane change probability as a value, for example, obtained by subtracting a vehicle height of the second vehicle 12 from a vehicle height of the first preceding vehicle 13b (vehicle height difference) becomes larger.
- a table similar to that of Fig. 8 is prepared in advance for the vehicle height too and stored in advance in the memory of the microcomputer.
- the probability compute part 105 is able to correct such that, with respect to the same vehicle height difference, the lane change probability decreases as the lane width (32a, 32b) becomes narrower.
- the probability compute part 105 may increase a weight applied to the vehicle height difference (an example of state quantities) as the lane width (32a, 32b) becomes narrower.
- the state quantity may be a relative speed of the second vehicle 12 with respect to the own vehicle 11.
- the larger the relative speed the easier the second vehicle 12 conducts a lane change.
- the smaller the relative speed the harder the second vehicle 12 conducts a lane change. Due to this, the probability compute part 105 computes, as the relative speed becomes smaller, a lower lane change probability.
- a table similar to that of Fig. 8 is prepared in advance for the relative speed too and is stored in advance in the memory of the microcomputer.
- the probability compute part 105 is able to correct such that, with respect to the same relative speed, the lane change probability decreases as the lane width (32a, 32b) becomes wider.
- the probability compute part 105 is able to compute a lane change probability according to a plurality of state quantities (x, ⁇ ) and weights ( ⁇ , ⁇ ) applied to lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )) computed according to the state quantities (x, ⁇ ). Namely, the probability compute part 105 computes, for the plurality of state quantities (x, ⁇ ), the lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )), respectively, and according to the lane width (32a, 32b), adjusts the weights ( ⁇ , ⁇ ) applied to the respective state quantities (x, ⁇ ).
- N is the number of corrected lane change probabilities or the sum of weights.
- L is a lane change probability according to a state quantity, for example, the above-mentioned acceleration, inter-vehicle distance, second vehicle size, or relative speed other than (x, ⁇ ).
- ⁇ in the below-mentioned expression (1) means, as mentioned above, an angle formed by a moving direction of the second vehicle 12 and a lane direction of the right lane G2 and x means the above-mentioned first proximity quantity or second proximity quantity.
- the movement prediction determine part 108 determines, according to the below-mentioned three methods (first method to third method), whether or not the second vehicle 12 conducts a lane change.
- the three methods are alternatively selectable.
- the movement prediction determine part 108 is able to compare a lane change probability corrected by the probability compute part 105 (called the "after-correction lane change probability") with a before-correction threshold value.
- the "before-correction threshold value" is a threshold value before corrected by the movement prediction determine part 108.
- the movement prediction determine part 108 determines that, if the after-correction lane change probability is greater than the before-correction threshold value, the second vehicle 12 conducts a lane change.
- the movement prediction determine part 108 determines that, if the after-correction lane change probability is equal to or smaller than the before-correction threshold value, the second vehicle 12 conducts no lane change.
- the movement prediction determine part 108 is not required to correct the threshold value according to the lane width (32a, 32b) of the adjacent lane (right lane G2).
- the movement prediction determine part 108 is able to compare a lane change probability computed by the probability compute part 105 with a threshold value corrected by the movement prediction determine part 108 (called the "after-correction threshold value").
- the lane change probability computed by the probability compute part 105 is a lane-change probability before correction by the probability compute part 105 (called the "before-correction lane change probability").
- the movement prediction determine part 108 determines that, if the before-correction lane change probability is greater than the after-correction threshold value, the second vehicle 12 conducts a lane change.
- the movement prediction determine part 108 determines that, if the before-correction lane change probability is equal to or smaller than the after-correction threshold value, the second vehicle 12 conducts no lane change.
- the probability compute part 105 is not required to correct the lane change probability according to the lane width (32a, 32b) of the adjacent lane (right lane G2).
- the movement prediction determine part 108 is able to compare the after-correction lane change probability with the after-correction threshold value. The movement prediction determine part 108 determines that, if the after-correction lane change probability is greater than the after-correction threshold value, the second vehicle 12 conducts a lane change. On the other hand, the movement prediction determine part 108 determines that, if the after-correction lane change probability is equal to or smaller than the after-correction threshold value, the second vehicle 12 conducts no lane change.
- the movement prediction determine part 108 compares one of the lane change probability and threshold value corrected according to the lane width (32a, 32b) with the other of the lane change probability and threshold value not corrected according to the lane width (32a, 32b). Alternatively, the movement prediction determine part 108 compares the lane change probability and threshold value both corrected according to the lane width (32a, 32b) with each other. The movement prediction determine part 108 determines, according to any one of these comparison results, whether or not the second vehicle 12 conducts a lane change.
- the threshold value correction according to the lane width (32a, 32b) will be explained.
- the movement prediction determine part 108 beforehand sets one or a plurality of threshold values for each lane width (32a, 32b). For example, for each of the narrow lane width 32a and wide lane width 32b, one or a plurality of threshold values are set. By the way, the set threshold values are stored in the memory of the microcomputer.
- the movement prediction determine part 108 selects one or a plurality of threshold values corresponding to a lane width obtained by the lane structure obtain part 104.
- the movement prediction determine part 108 beforehand sets different threshold values for lane widths, respectively, and selects from among the threshold values a threshold value corresponding to an actual lane width, thereby achieving the threshold value correction.
- the movement prediction determine part 108 compares the selected threshold value (an example of the after-correction threshold value) with a lane change probability and predicts a lane change of the second vehicle 12.
- “Setting a plurality of threshold values” is to set threshold values for state quantities, respectively, used to compute a lane change probability. For example, as explained with reference to the expression (1), in the case of using a plurality of state quantities (x, ⁇ , ...) to compute a lane change probability, threshold values are set for the state quantities (x, ⁇ , %), respectively.
- the movement prediction determine part 108 compares, for each of the state quantities (x, ⁇ , %), a selected threshold value with a lane change probability ( ⁇ (x), ⁇ ( ⁇ ), ...) and determines whether or not the second vehicle 12 conducts a lane change.
- “Setting a plurality of threshold values” is to set, for multistage-controlling the first inter-vehicle distance (38a, 38b) or the speed of the own vehicle 11, a plurality of threshold values for a state quantity used to compute a lane change probability or for the lane change probability. More precisely, a plurality of threshold values are beforehand prepared in a multistage manner. Then, the plurality of threshold values are compared with a lane change probability, to determine in a multistage manner whether or not the second vehicle 12 conducts a lane change. This realizes a multistage vehicle control of the own vehicle 11 for securing safety for the lane change of the second vehicle 12.
- the probability compute part 105 may suppose that the second vehicle 12 is positioned on the lane boundary line 31 and compute a lane change probability.
- the position of the second vehicle 12 that is an example of a state quantity used to compute a lane change probability is supposed to be a position on the lane boundary line 31. Taking the position of the second vehicle 12 into consideration, the computation of a lane change probability or the determination of a lane change can be stabilized.
- the own vehicle path generate part 109 generates a path of the own vehicle 11 according to the movement (including the lane change) of the second vehicle 12 predicted by the movement prediction determine part 108. If the lane change of the second vehicle 12 to the own lane G1 has been predicted, it is possible to generate a path based on the lane change prediction of the second vehicle 12. Accordingly, it is possible to generate a smooth path of the own vehicle 11 that secures a sufficient inter-vehicle distance from the second vehicle 12 and prevents the movement of the second vehicle 12 from causing a rapid deceleration or rapid steering of the own vehicle 11.
- the "path of the own vehicle” indicates not only a positional profile of the own vehicle 11 at different times but also a speed profile of the own vehicle 11 at respective positions.
- the own vehicle path generate part 109 generates a path of the own vehicle 11 conforming to the lane change. Further, it is possible to generate a path of the own vehicle 11 to increase a relative distance of the second vehicle 12 with respect to the own vehicle 11. Also, if there is formed a train of vehicles in front of the own vehicle 11, the own vehicle path generate part 109 may compute a path of the own vehicle 11 that makes the own vehicle 11 decelerate to form an inter-vehicle space so that the second vehicle 12 may cut in the train of vehicles. This results in more safely controlling the own vehicle 11.
- the vehicle control part 110 drives at least one of a steering actuator, an acceleration pedal actuator, and a brake pedal actuator according to an own position computed by the own vehicle position estimate part 101, so that the own vehicle 11 may run along the path generated by the own vehicle path generate part 109.
- the first embodiment describes a control example that controls the own vehicle 11 along a path. Instead, it is possible to control the own vehicle 11 without generating a path of the own vehicle 11. In this case, it is possible to achieve the control according to a relative distance with respect to the second vehicle 12 or an attitude angle difference between the second vehicle 12 and the own vehicle 11.
- the vehicle control part 110 is able to carry out a multistage vehicle control of the own vehicle 11 to secure safety with respect to a lane change of the second vehicle 12.
- the value itself of the lane change probability may be used to control an inter-vehicle distance between the own vehicle 11 and the second vehicle 12 and a vehicle speed of the own vehicle 11.
- Figure 2 is repeatedly executed at predetermined intervals from when an ignition switch of the own vehicle 11 is turned ON (in the case of an electric car, a power source is turned ON) until when it is turned OFF. Also, the control flow of Fig. 2 is based on an assumption that the own vehicle 11 is run by automated driving.
- step S201 the own vehicle position estimate part 101 measures an own position (an absolute position and a relative position) of the own vehicle 11. Thereafter, the position and attitude of the own vehicle 11 on a map are detected.
- the object detect part 102 obtains a behavior of the second vehicle 12. More precisely, the object detect part 102 employs an object detect sensor to detect the second vehicle 12 and tracks the second vehicle 12. As a detection result, for example, a behavior of the second vehicle 12 in a top view seen from the air above the own vehicle 11 is outputted.
- the lane structure obtain part 104 obtains information indicating the structure of a road around the own vehicle 11 and the structure of each lane (G1, G2) forming the road.
- information indicating the structure of an adjacent lane (right lane G2) in which the second vehicle 12, i.e., a lane change determination object is running is at least obtained.
- the structure of the adjacent lane (right lane G2) includes a lane width of the adjacent lane (right lane G2). From map data or an analysis of an image around the own vehicle 11, the information indicating the road structure and lane structure is obtainable.
- the movement option generate part 103 predicts, according to the road structure and lane structure, movement options to be carried out in the near future by the second vehicle 12.
- the movement options include a lane change.
- step S205 the motion prediction apparatus of other vehicle determines whether or not a lane change is included in the predicted movement options. If there is the lane change (YES in S205), it advances to step S206. On the other hand, if there is no lane change (NO in S205), it advances to step S213 in which the vehicle control part 110 executes a normal vehicle control without using a determination result by the motion prediction apparatus of other vehicle.
- the motion prediction apparatus of other vehicle determines, according to a user selected state in connection with a lane change probability correction, whether or not a lane change probability must be corrected. If the user has selected to correct the lane change probability according to the lane width (32a, 32b) (YES in S206), it advances to step S207. On the other hand, if the user has selected not to correct the lane change probability according to the lane width (32a, 32b) (NO in S206), it advances to step S208.
- the probability compute part 105 computes a lane change probability according to a state quantity.
- the state quantity is one or a combination of two or more of an attitude of the second vehicle 12, a moving direction thereof, an angle ⁇ thereof, a first proximity quantity, a second proximity quantity, an acceleration of the second vehicle 12, a proximity degree of the second vehicle 12 with respect to the first preceding vehicle 13a, a first inter-vehicle distance (38a, 38b), a second inter-vehicle distance (39a, 39b), a size of the second vehicle 12 or first preceding vehicle (13a, 13b), and a relative speed of the second vehicle 12 with respect to the own vehicle 11. Thereafter, it advances to step S210.
- the probability compute part 105 computes, similar to the step S208, a lane change probability according to a state quantity. Further, the probability compute part 105 corrects the lane change probability according to the lane width (32a, 32b) of the adjacent lane (right lane G2). More precisely, the probability compute part 105 changes, according to the lane width (32a, 32b), a weight applied to the state quantity used to compute the lane change probability, thereby correcting the lane change probability. Thereafter, it advances to step S209.
- the motion prediction apparatus of other vehicle determines, according to a user selected state concerning a threshold value correction, whether or not a threshold value must be corrected. If correcting the threshold value according to the lane width (32a, 32b) has been selected by the user (YES in S209), it advances to step S210. On the other hand, if not correcting the threshold value according to the lane width (32a, 32b) has been selected by the user (NO in S209), it advances to step S211.
- the movement prediction determine part 108 compares the lane change probability corrected in the step S207 (after-correction lane change probability) with a before-correction threshold value. If the after-correction lane change probability is greater than the before-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the after-correction lane change probability is equal to or smaller than the before-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change. Thereafter, it advances to step S212.
- the movement prediction determine part 108 first corrects the threshold value according to the lane width (32a, 32b) of the adjacent lane (right lane G2). Then, if the step S208 has been passed through, the movement prediction determine part 108 compares the lane change probability computed in the step S208 (before-correction lane change probability) with the corrected threshold value (after-correction threshold value). If the before-correction lane change probability is greater than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the before-correction lane change probability is equal to or smaller than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change.
- the movement prediction determine part 108 compares the lane change probability corrected in the step S207 (after-correction lane change probability) with the after-correction threshold value. If the after-correction lane change probability is greater than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the after-correction lane change probability is equal to or smaller than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change. Thereafter, it advances to step S212.
- the own vehicle path generate part 109 generates a path of the own vehicle 11 according to the movement of the second vehicle 12 predicted in the step S210 or S211. If the lane change of the second vehicle 12 to the own lane G1 has been predicted, the path is generated based on the lane change prediction of the second vehicle 12. As the path of the own vehicle 11, the own vehicle path generate part 109 determines a relative distance of the second vehicle 12 with respect to the own vehicle 11 and determines a locus and vehicle speed of the own vehicle 11 that are necessary to maintain the relative distance.
- the vehicle control part 110 drives various kinds of actuators according to the own position computed by the own vehicle position estimate part 101, so that the own vehicle 11 may run along the path generated in the step S212.
- the vehicle control part 110 may control the own vehicle 11 without generating the path of the own vehicle 11.
- a vehicle runs through locations with different road widths and lane widths. If the lane width differs, the movement of the second vehicle 12 conducting a lane change will differ. Due to this, the motion prediction apparatus of other vehicle corrects, according to the lane width (32a, 32b), at least one of the lane change probability and threshold value.
- the movement prediction determine part 108 compares one of the lane change probability and threshold value corrected according to the lane width with the other of the lane change probability and threshold value not corrected according to the lane width. Alternatively, the movement prediction determine part 108 compares the lane change probability and threshold value both corrected according to the lane width with each other.
- the movement prediction determine part 108 determines whether or not the second vehicle 12 conducts a lane change. Predicting the lane change by taking the lane width (32a, 32b) of the adjacent lane G2 into consideration is able to suppress an erroneous lane change prediction or a prediction delay. Further, it suppresses a deceleration of the own vehicle 11 due to the erroneous prediction or a sudden deceleration of the own vehicle 11 due to the prediction delay.
- the probability compute part 105 changes, according to the lane width, a weight applied to a lane change probability computed according to a state quantity, thereby correcting the lane change probability according to the lane width. Even on roads with different lane widths, it is possible to compute a lane change probability without receiving an influence of the lane widths.
- the state quantity may be a position of the second vehicle 12, a first proximity quantity, i.e., an approaching quantity of the second vehicle 12 to the own vehicle 11, or a second proximity quantity, i.e., an approaching quantity of the second vehicle 12 to the lane boundary line 31.
- the probability compute part 105 increases, as the lane width becomes wider, a weight applied to the position of the second vehicle 12, first proximity quantity, and second proximity quantity. As the lane width becomes wider, it is possible, in determining a lane change, to attach importance to the position of the second vehicle 12, first proximity quantity, and second proximity quantity. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be an attitude of the second vehicle 12, a moving direction of the second vehicle 12, or an angle ⁇ formed by the moving direction of the second vehicle 12 and a lane direction of the right lane G2.
- the probability compute part 105 increases, as the lane width becomes narrower, a weight applied to the attitude, moving direction, or angle ⁇ . As the lane width becomes narrower, it is possible, in determining a lane change, to attach importance to the attitude, moving direction, or angle ⁇ . Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be an acceleration of the second vehicle 12 or a proximity degree of the second vehicle 12 with respect to the first preceding vehicle 13a.
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes narrower, a weight applied to the acceleration or proximity degree. As the lane width becomes narrower, it is possible, in determining a lane change, to attach importance to the acceleration or proximity degree. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 6A and 6B , the first inter-vehicle distance (38a, 38b).
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes wider, a weight applied to the first inter-vehicle distance. As the lane width becomes wider, it is possible, in determining a lane change, to attach importance to the first inter-vehicle distance. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 7A to 7C , the second inter-vehicle distance (39a, 39b).
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes wider, a weight applied to the second inter-vehicle distance. As the lane width becomes wider, it is possible, in determining a lane change, to attach importance to the second inter-vehicle distance. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 5A and 5C , a size of the second vehicle 12, a size of the first preceding vehicle (13a, 13b), or a vehicle height difference.
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes narrower, a weight applied to the size of the second vehicle 12, the size of the first preceding vehicle (13a, 13b), or the vehicle height difference.
- the lane width becomes narrower, it is possible, in determining a lane change, to attach importance to the size of the second vehicle 12, the size of the first preceding vehicle (13a, 13b), or the vehicle height difference. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the state quantity may be a relative speed of the second vehicle 12 with respect to the own vehicle 11.
- the probability compute part 105 increases, as the lane width (32a, 32b) becomes wider, a weight applied to the relative speed. As the lane width becomes wider, it is possible, in determining a lane change, to attach importance to the relative speed. Without receiving an influence of the lane width, a proper lane change probability can be computed.
- the probability compute part 105 computes, according to state quantities (x, ⁇ ) and weights ( ⁇ , ⁇ ) applied to the state quantities, respectively, respective lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )).
- the weights ( ⁇ , ⁇ ) applied to the above-mentioned state quantities are adjusted according to a lane width and a plurality of after-correction lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )) are computed.
- the plurality of after-correction lane change probabilities are used with the expression (1) to compute one after-correction lane change probability (P). With this, a computation accuracy of the lane change probability improves.
- the movement prediction determine part 108 sets, for each lane width, one or a plurality of threshold values and selects one or a plurality of threshold values corresponding to the lane width indicated by the information obtained by the lane structure obtain part 104.
- the movement prediction determine part 108 compares the selected threshold value (an example of the after-correction threshold value) with the lane change probability and predicts a lane change to be conducted by the second vehicle 12. Without receiving an influence of the lane width, the lane change is properly predictable.
- To set a plurality of threshold values is to set threshold values for state quantities, respectively, used to compute a lane change probability.
- the movement prediction determine part 108 compares, for each of the state quantities (x, ⁇ , 7), a selected threshold value with a lane change probability ( ⁇ (x), ⁇ ( ⁇ ), ...), thereby determining whether or not the second vehicle 12 conducts a lane change. Without receiving an influence of the lane width, the lane change is properly predictable.
- To set a plurality of threshold values is, for multistage-controlling the first inter-vehicle distance (38a, 38b) or the speed of the own vehicle 11, to set a plurality of threshold values for a state quantity used to compute a lane change probability or for the lane change probability. Without receiving an influence of the lane width, a multistage vehicle control of the own vehicle 11 is realizable to secure safety with respect to the lane change of the second vehicle 12.
- the probability compute part 105 may compute a lane change probability on an assumption that the second vehicle 12 is positioned on the lane boundary line 31. Without receiving an influence of the lane width, the lane change probability is properly computable.
- the motion prediction apparatus of other vehicle and the motion prediction method of other vehicle according to the second embodiment differ from those of the first embodiment in that they correct at least one of the lane change probability and threshold value according to a position of the second vehicle in the adjacent lane G2 instead of the lane width (32a, 32b) of the adjacent lane G2.
- the vehicles (11, 12) are supposed to usually run at a lane width directional center of the respective lanes (G1, G2). Accordingly, if the lane width (32a, 32b) changes, the position of the second vehicle 12 with respect to the own vehicle 11 or the lane boundary line 31 changes accordingly.
- a lane width directional distance from the own vehicle 11 or the lane boundary line 31 to the second vehicle 12 i.e., the relative position of the second vehicle 12 with respect to the own vehicle 11 or the lane boundary line 31 changes accordingly. Due to this, instead of the lane width (32a, 32b) of the adjacent lane G2, the lane width directional position of the second vehicle 12 with respect to the own vehicle 11 or the lane boundary line 31 is used to correct at least one of the lane change probability or threshold value, thereby providing functions and effects similar to those of the first embodiment.
- the motion prediction apparatus of other vehicle and the motion prediction method of other vehicle according to the second embodiment effectively function in, for example, the running scenes illustrated in Figs. 4A and 4B .
- the running scenes such as those illustrated in Figs. 4A and 4B are examples of running scenes in which the motion prediction method of other vehicle and the motion prediction of apparatus other vehicle according to the second embodiment effectively function and are not intended to limit the scope of application of the motion prediction method of other vehicle and the motion prediction apparatus of other vehicle according to the second embodiment.
- the second embodiment computes a lane change probability according to a state quantity of the second vehicle 12 and uses the lane change probability and a threshold value to predict a lane change to be conducted by the second vehicle 12. In other words, it employs the lane change probability and threshold value to determine whether or not the second vehicle 12 conducts a lane change.
- a difference will occur in a state quantity of the second vehicle 12 when conducting a course change.
- state quantities such as the attitude (yaw angle with respect to the lane boundary line 31), moving direction, lane width directional moving distance (approaching quantity), and running locus of the second vehicle 12 change according to the position of the second vehicle 12.
- the second embodiment obtains a lane width directional position of the second vehicle 12 with respect to the own vehicle 11 or a position of the second vehicle 12 with respect to the lane boundary line 31 and, according to the position of the second vehicle 12, corrects at least one of the lane change probability and threshold value. Thereafter, the second embodiment compares the after-correction lane change probability with the before-correction threshold value, or compares the before-correction lane change probability with the after-correction threshold value, or compares the after-correction lane change probability with the after-correction threshold value, thereby predicting a lane change to be conducted by the second vehicle 12. Predicting a lane change by taking into account a position of the second vehicle 12 is able to suppress an erroneous lane change prediction or a prediction delay.
- the configuration of the motion prediction apparatus of other vehicle according to the second embodiment differs from the configuration of the motion prediction apparatus of other vehicle of the first embodiment in the below-mentioned points.
- the probability compute part 105 corrects a lane change probability according to a position of the second vehicle 12 (i.e., a lane width directional distance from the own vehicle 11 or lane boundary line 31 to the second vehicle 12). For example, the probability compute part 105 changes a weight applied to a state quantity used to compute a lane change probability according to a lane width directional distance (33a, 33b, 34a, 34b) from the own vehicle 11 or lane boundary line 31 to the second vehicle 12. For example, if the distance (33a, 34a) is short, it is presumed that the second vehicle 12 conducts a lane change at an angle ⁇ (state) smaller than that when the distance (33b, 34b) is long.
- the probability compute part 105 increases a weight applied to the angle ⁇ as the distance (33a, 33b, 34a, 34b) becomes shorter. In other words, the nearer the position of the second vehicle 12 to the own vehicle 11 or lane boundary line 31, the heavier the weight applied to the angle ⁇ is increased.
- the probability compute part 105 may change, similar to the case of the angle ⁇ , a weight applied to an attitude of the second vehicle 12 or a moving direction of the second vehicle 12 according to the position of the second vehicle 12.
- the probability compute part 105 adjusts a weight applied to the state quantity according to the position of the second vehicle 12 instead of the lane width (32a, 32b).
- the state quantity may be an acceleration of the second vehicle 12 or a proximity degree of the second vehicle 12 with respect to the first preceding vehicle 13a running in front of the second vehicle 12 in the adjacent lane (right lane G2).
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes nearer to the own vehicle 11 or lane boundary line 31, a weight applied to the acceleration or proximity degree.
- the state quantity may be, as illustrated in Figs. 6A and 6B , the first inter-vehicle distance (38a, 38b).
- the probability compute part 105 increases a weight applied to the first inter-vehicle distance as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31.
- the state quantity may be, as illustrated in Figs. 7A to 7C , the second inter-vehicle distance (39a, 39b).
- the probability compute part 105 increases a weight applied to the second inter-vehicle distance (39a, 39b) as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31.
- the state quantity may be, as illustrated in Figs. 5A and 5C , a size of the second vehicle 12 and a size of the first preceding vehicle (13a, 13b).
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes nearer to the own vehicle 11 or lane boundary line 31, a weight applied to the size of the second vehicle 12 and the size of the first preceding vehicle (13a, 13b).
- the state quantity may be a relative speed of the second vehicle 12 with respect to the own vehicle 11.
- the probability compute part 105 increases a weight applied to the relative speed as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31.
- the probability compute part 105 may compute one lane change probability (P) according to state quantities (x, ⁇ ) and weights ( ⁇ , ⁇ ) applied to the state quantities (x, ⁇ ).
- the movement prediction determine part 108 corrects a threshold value according to the position of the second vehicle 12. For example, the movement prediction determine part 108 corrects the threshold value according to the lane width directional distance (33a, 33b, 34a, 34b) from the own vehicle 11 or lane boundary line 31 to the second vehicle 12.
- the movement prediction determine part 108 beforehand sets one or a plurality of threshold values for each position of the second vehicle 12. For example, for each of the short distance (33a, 34a) and long distance (33b, 34b), one or a plurality of threshold values are set. The movement prediction determine part 108 selects one or a plurality of threshold values corresponding to a distance (33a, 33b, 34a, 34b) obtained by the lane structure obtain part 104. In this way, the movement prediction determine part 108 beforehand sets different threshold values for each position of the second vehicle 12 and selects, from among the threshold values, a threshold value corresponding to an actual position of the second vehicle 12, thereby correcting the threshold value.
- the configuration of the motion prediction apparatus of other vehicle according to the second embodiment is the same as, except the above-mentioned points, the configuration of the motion prediction apparatus of other vehicle according to the first embodiment explained with reference to Fig. 1 .
- Figure 3 is repeatedly executed at predetermined intervals from when the ignition switch of the own vehicle 11 is turned ON (in the case of an electric car, a power source is turned ON) until when it is turned OFF. Also, a control flow of Fig. 3 is based on an assumption that the own vehicle 11 is run by automated driving.
- Steps S301 to S305 execute the same processing operations as those of the steps S201 to S205 of Fig. 2 .
- step S306 the motion prediction apparatus of other vehicle determines, according to a user selected state in connection with a lane change probability correction, whether or not a lane change probability must be corrected. If the user has selected to correct the lane change probability according to a position of the second vehicle 12 (YES in S306), it advances to step S307. On the other hand, if the user has selected not to correct the lane change probability according to a position of the second vehicle 12 (NO in S306), it advances to step S308.
- the probability compute part 105 computes a lane change probability according to a state quantity.
- the state quantity is one or a combination of two or more of the attitude, moving direction, and angle ⁇ of the second vehicle 12, an acceleration of the second vehicle 12, a proximity degree of the second vehicle 12 with respect to the first preceding vehicle 13a, a first inter-vehicle distance (38a, 38b), a second inter-vehicle distance (39a, 39b), a size of the second vehicle 12 or first preceding vehicle (13a, 13b), and a relative speed of the second vehicle 12 with respect to the own vehicle 11. Thereafter, it advances to step S310.
- the probability compute part 105 computes, similar to the step S308, a lane change probability according to a state quantity. Further, the probability compute part 105 corrects the lane change probability according to a position of the second vehicle 12. More precisely, the probability compute part 105 changes, according to the position of the second vehicle 12, a weight applied to the state quantity used to compute the lane change probability, thereby correcting the lane change probability. Thereafter, it advances to step S309.
- the motion prediction apparatus of other vehicle determines, according to a user selected state concerning a threshold value correction, whether or not a threshold value must be corrected. If correcting the threshold value according to the position of the second vehicle 12 has been selected by the user (YES in S309), it advances to step S310. On the other hand, if not correcting the threshold value according to the position of the second vehicle 12 has been selected by the user (NO in S309), it advances to step S311.
- the movement prediction determine part 108 compares the lane change probability corrected in the step S307 (after-correction lane change probability) with a before-correction threshold value. If the after-correction lane change probability is greater than the before-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the after-correction lane change probability is equal to or smaller than the before-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change. Thereafter, it advances to step S312.
- the movement prediction determine part 108 first corrects the threshold value according to the position of the second vehicle 12. Then, if the step S308 has been passed through, the movement prediction determine part 108 compares the lane change probability computed in the step S308 (before-correction lane change probability) with the corrected threshold value (after-correction threshold value). If the before-correction lane change probability is greater than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the before-correction lane change probability is equal to or smaller than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change.
- the movement prediction determine part 108 compares the lane change probability corrected in the step S307 (after-correction lane change probability) with the after-correction threshold value. If the after-correction lane change probability is greater than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts a lane change. On the other hand, if the after-correction lane change probability is equal to or smaller than the after-correction threshold value, the movement prediction determine part 108 determines that the second vehicle 12 conducts no lane change. Thereafter, it advances to step S312.
- a vehicle runs through locations with different road widths and lane widths. If the lane width differs, the position of the second vehicle 12 with respect to the own vehicle 11 or lane boundary line 31 changes, and also, the movement of the second vehicle 12 when conducting a lane change differs. Due to this, the motion prediction apparatus of other vehicle corrects, according to a position of the second vehicle 12 in a lane width direction with respect to the own vehicle 11 or lane boundary line 31, at least one of the lane change probability and threshold value.
- the movement prediction determine part 108 compares one of the lane change probability and threshold value corrected according to the position of the second vehicle 12 with the other of the lane change probability and threshold value not corrected according to the position of the second vehicle 12. Alternatively, the movement prediction determine part 108 compares the lane change probability and threshold value both corrected according to the position of the second vehicle 12 with each other. According to any one of the comparison results, the movement prediction determine part 108 determines whether or not the second vehicle 12 conducts a lane change. Predicting a lane change by taking into account the lane width (32a, 32b) of the adjacent lane G2 is able to suppress an erroneous lane change prediction or a prediction delay. Further, it suppresses a deceleration of the own vehicle 11 due to an erroneous prediction or a sudden deceleration of the own vehicle 11 due to a prediction delay.
- the probability compute part 105 changes a weight applied to a state quantity according to a position of the second vehicle 12, thereby correcting a lane change probability according to the position of the second vehicle 12. Even on roads with different lane widths, it is possible to compute a lane change probability without receiving an influence of the lane widths.
- the state quantity may be an attitude of the second vehicle 12, a moving direction of the second vehicle 12, or an angle ⁇ formed by the moving direction of the second vehicle 12 and a lane direction of the right lane G2.
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes closer to the own vehicle 11 or lane boundary line 31, a weight applied to the attitude, moving direction, or angle ⁇ . As the position of the second vehicle 12 becomes nearer to the own vehicle 11 or lane boundary line 31, it is possible, in determining a lane change, to attach importance to the attitude, moving direction, or angle ⁇ . Without receiving an influence of lane widths, a proper lane change probability can be computed.
- the state quantity may be an acceleration of the second vehicle 12 or a proximity degree of the second vehicle 12 with respect to the first preceding vehicle 13a.
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes nearer to the own vehicle 11 or lane boundary line 31, a weight applied to the acceleration or proximity degree. As the position of the second vehicle 12 becomes nearer to the own vehicle or lane boundary line 31, it is possible, in determining a lane change, to attach importance to the acceleration or proximity degree. Without receiving an influence of lane widths, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 6A and 6B , the first inter-vehicle distance (38a, 38b).
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, a weight applied to the first inter-vehicle distance. As the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, it is possible, in determining a lane change, to attach importance to the first inter-vehicle distance. Without receiving an influence of lane widths, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 7A to 7C , the second inter-vehicle distance (39a, 39b).
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, a weight applied to the second inter-vehicle distance. As the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, it is possible, in determining a lane change, to attach importance to the second inter-vehicle distance. Without receiving an influence of lane widths, a proper lane change probability can be computed.
- the state quantity may be, as illustrated in Figs. 5A and 5C , the size of the second vehicle 12, the size of the first preceding vehicle (13a, 13b), or a vehicle height difference.
- the probability compute part 105 increases, as the position of the second vehicle becomes nearer to the own vehicle 11 or lane boundary line 31, a weight applied to the size of the second vehicle 12, the size of the first preceding vehicle (13a, 13b), or the vehicle height difference.
- the state quantity may be a relative speed of the second vehicle 12 with respect to the own vehicle 11.
- the probability compute part 105 increases, as the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, a weight applied to the relative speed. As the position of the second vehicle 12 becomes farther from the own vehicle 11 or lane boundary line 31, it is possible, in determining a lane change, to attach importance to the relative speed. Without receiving an influence of lane widths, a proper lane change probability can be computed.
- the probability compute part 105 computes, according to state quantities (x, ⁇ ), respective lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )). Weights ( ⁇ , ⁇ ) applied to the above-mentioned state quantities are adjusted according to a lane width and a plurality of after-correction lane change probabilities ( ⁇ (x), ⁇ ( ⁇ )) are computed. The plurality of after-correction lane change probabilities are used with the expression (1) to compute one after-correction lane change probability (P). With this, a computation accuracy of the lane change probability improves.
- the movement prediction determine part 108 sets, for each position of the second vehicle 12, one or a plurality of threshold values and selects one or a plurality of threshold values corresponding to a position of the second vehicle 12 indicated by information obtained by the lane structure obtain part 104.
- the movement prediction determine part 108 compares the selected threshold value (an example of an after-correction threshold value) with the lane change probability and predicts a lane change to be conducted by the second vehicle 12. Without receiving an influence of lane widths, the lane change is properly predictable.
- To set a plurality of threshold values is to set threshold values for state quantities used for computing a lane change probability, respectively.
- the movement prediction determine part 108 compares, for each of the state quantities (x, ⁇ , 7), a selected threshold value with a lane change probability ( ⁇ (x), ⁇ ( ⁇ ), ...), thereby determining whether or not the second vehicle 12 conducts a lane change. Without receiving an influence of lane widths, the lane change is properly predictable.
- To set a plurality of threshold values is to set, for multistage-controlling the first inter-vehicle distance (38a, 38b) or the speed of the own vehicle 11, a plurality of threshold values for state quantities used to compute a lane change probability or for a lane change probability. Without receiving an influence of lane widths, a multistage vehicle control of the own vehicle 11 is realizable to secure safety with respect to a lane change of the second vehicle 12.
- the processing circuits include programmed processing devices such as processing devices containing electric circuits. Also, the processing devices include application specific integrated circuits (ASICs) and conventional circuit parts arranged to execute the functions mentioned in the embodiments.
- ASICs application specific integrated circuits
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2019/000177 WO2020161512A1 (ja) | 2019-02-07 | 2019-02-07 | 他車動作予測方法及び他車動作予測装置 |
Publications (3)
Publication Number | Publication Date |
---|---|
EP3925845A1 true EP3925845A1 (de) | 2021-12-22 |
EP3925845A4 EP3925845A4 (de) | 2022-04-20 |
EP3925845B1 EP3925845B1 (de) | 2023-10-11 |
Family
ID=71947539
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19914188.8A Active EP3925845B1 (de) | 2019-02-07 | 2019-02-07 | Verfahren zur vorhersage der aktion eines anderen fahrzeugs und vorrichtung zur vorhersage der aktion eines anderen fahrzeugs |
Country Status (6)
Country | Link |
---|---|
US (1) | US20220105929A1 (de) |
EP (1) | EP3925845B1 (de) |
JP (1) | JPWO2020161512A1 (de) |
CN (1) | CN113412212A (de) |
RU (1) | RU2770230C1 (de) |
WO (1) | WO2020161512A1 (de) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4173915A1 (de) * | 2021-10-26 | 2023-05-03 | Tusimple, Inc. | Systeme und verfahren zur handhabung von cut-in-verkehr für autonomes fahren |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2760050C1 (ru) * | 2018-12-11 | 2021-11-22 | Ниссан Мотор Ко., Лтд. | Способ предсказания действий другого транспортного средства и устройство предсказания действий другого транспортного средства |
DE102019122249A1 (de) * | 2019-08-19 | 2021-02-25 | Zf Friedrichshafen Ag | Verfahren zum Ermitteln eines Fahrspurwechsels, Fahrassistenzsystem und Fahrzeug |
US11860634B2 (en) * | 2019-12-12 | 2024-01-02 | Baidu Usa Llc | Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes |
DE102021109425B3 (de) * | 2021-04-15 | 2022-07-21 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren zum Steuern eines Fahrzeugs und Steuervorrichtung für ein Fahrzeug |
JP2023047174A (ja) * | 2021-09-24 | 2023-04-05 | トヨタ自動車株式会社 | 車両用表示制御装置、車両用表示装置、車両、車両用表示制御方法及びプログラム |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4066573B2 (ja) * | 1999-09-22 | 2008-03-26 | 株式会社デンソー | 先行車選択装置、車間制御装置及び記録媒体 |
JP4282858B2 (ja) * | 1999-12-17 | 2009-06-24 | 日産自動車株式会社 | 車両用走行制御装置 |
JP2001199260A (ja) | 2000-01-20 | 2001-07-24 | Matsushita Electric Ind Co Ltd | 車間距離制御装置、車両走行状況表示装置、車速制御解除装置、及び車両急制動警告装置 |
JP4400316B2 (ja) * | 2004-06-02 | 2010-01-20 | 日産自動車株式会社 | 運転意図推定装置、車両用運転操作補助装置および車両用運転操作補助装置を備えた車両 |
CN100492437C (zh) * | 2007-06-01 | 2009-05-27 | 清华大学 | 一种目标车换道工况下的快速识别方法 |
JP4990424B2 (ja) * | 2010-04-15 | 2012-08-01 | 三菱電機株式会社 | 走行支援装置 |
DE102013104256A1 (de) * | 2013-04-26 | 2014-10-30 | Conti Temic Microelectronic Gmbh | Verfahren und Vorrichtung zur Schätzung der Anzahl von Fahrspuren |
JP6313198B2 (ja) * | 2014-11-28 | 2018-04-18 | 株式会社デンソー | 車両制御装置 |
JP6404722B2 (ja) * | 2015-01-21 | 2018-10-17 | 株式会社デンソー | 車両の走行制御装置 |
JP6497284B2 (ja) * | 2015-09-15 | 2019-04-10 | 株式会社デンソー | 車両制御装置、及び車両制御方法 |
JP6512137B2 (ja) * | 2016-03-02 | 2019-05-15 | トヨタ自動車株式会社 | 車両走行制御装置 |
DE102016009762A1 (de) * | 2016-08-11 | 2018-02-15 | Trw Automotive Gmbh | Steuerungssystem und Steuerungsverfahren zum Ermitteln einer Wahrscheinlichkeit für einen Fahrspurwechsel eines vorausfahrenden Kraftfahrzeugs |
JP6494121B2 (ja) * | 2017-03-01 | 2019-04-03 | 本田技研工業株式会社 | 車線変更推定装置、車線変更推定方法、およびプログラム |
JP6943005B2 (ja) * | 2017-04-17 | 2021-09-29 | 日産自動車株式会社 | 車線変更判定方法及び車線変更判定装置 |
-
2019
- 2019-02-07 CN CN201980091535.5A patent/CN113412212A/zh active Pending
- 2019-02-07 EP EP19914188.8A patent/EP3925845B1/de active Active
- 2019-02-07 JP JP2020570655A patent/JPWO2020161512A1/ja active Pending
- 2019-02-07 RU RU2021126161A patent/RU2770230C1/ru active
- 2019-02-07 US US17/428,874 patent/US20220105929A1/en not_active Abandoned
- 2019-02-07 WO PCT/IB2019/000177 patent/WO2020161512A1/ja unknown
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4173915A1 (de) * | 2021-10-26 | 2023-05-03 | Tusimple, Inc. | Systeme und verfahren zur handhabung von cut-in-verkehr für autonomes fahren |
Also Published As
Publication number | Publication date |
---|---|
JPWO2020161512A1 (de) | 2020-08-13 |
WO2020161512A1 (ja) | 2020-08-13 |
US20220105929A1 (en) | 2022-04-07 |
RU2770230C1 (ru) | 2022-04-14 |
EP3925845B1 (de) | 2023-10-11 |
EP3925845A4 (de) | 2022-04-20 |
CN113412212A (zh) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3925845B1 (de) | Verfahren zur vorhersage der aktion eines anderen fahrzeugs und vorrichtung zur vorhersage der aktion eines anderen fahrzeugs | |
US11220261B2 (en) | Method for assisting a driver, driver assistance system, and vehicle including such driver assistance system | |
US10102761B2 (en) | Route prediction device | |
EP3288005B1 (de) | Vorrichtung zur okklusionskontrolle | |
US11719549B2 (en) | Vehicle control apparatus | |
US20190016339A1 (en) | Vehicle control device, vehicle control method, and vehicle control program | |
CN113243029B (zh) | 其他车辆动作预测方法及其他车辆动作预测装置 | |
US20200317192A1 (en) | Vehicle control device | |
US20200238980A1 (en) | Vehicle control device | |
US11845471B2 (en) | Travel assistance method and travel assistance device | |
EP1975903A2 (de) | Ausrüstung und Verfahren zur Vermeidung von Fahrzeugkollisionen | |
US11708069B2 (en) | Obstacle avoidance apparatus and obstacle avoidance route generating apparatus | |
US20200070818A1 (en) | Collision avoidance apparatus | |
US20200353918A1 (en) | Vehicle control device | |
JPWO2020025991A1 (ja) | 走行軌跡補正方法、走行制御方法、及び走行軌跡補正装置 | |
KR20190045308A (ko) | 차량 판정 방법, 주행 경로 보정 방법, 차량 판정 장치, 및 주행 경로 보정 장치 | |
US20220314968A1 (en) | Electronic control device | |
US11295609B1 (en) | Travel assistance method and travel assistance device | |
EP4045370A1 (de) | Adaptive geschwindigkeitsregelung | |
CN113409614B (zh) | 推定装置 | |
EP4112404A1 (de) | Fahrzeugsteuerungsverfahren und fahrzeugsteuerungsvorrichtung | |
JP3868922B2 (ja) | 車間距離制御装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20210831 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: RENAULT S.A.S Owner name: NISSAN MOTOR CO., LTD. |
|
A4 | Supplementary search report drawn up and despatched |
Effective date: 20220317 |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06V 20/56 20220101ALI20220311BHEP Ipc: B60W 40/04 20060101AFI20220311BHEP |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: RENAULT S.A.S Owner name: NISSAN MOTOR CO., LTD. |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20221013 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
INTG | Intention to grant announced |
Effective date: 20230426 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE PATENT HAS BEEN GRANTED |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: RENAULT S.A.S |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602019039396 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG9D |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20231011 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 1619944 Country of ref document: AT Kind code of ref document: T Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240112 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240211 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240211 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240112 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240111 Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240212 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20240226 Year of fee payment: 6 Ref country code: GB Payment date: 20240221 Year of fee payment: 6 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20240111 Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20240227 Year of fee payment: 6 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20231011 |